Feature-level or decision-level fusion of CNN video features and audio descriptors via SVR achieves CCC 0.749 (arousal) and 0.565 (valence) on RECOLA after preprocessing and post-processing.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Emotion Recognition Using Fusion of Audio and Video Features
Feature-level or decision-level fusion of CNN video features and audio descriptors via SVR achieves CCC 0.749 (arousal) and 0.565 (valence) on RECOLA after preprocessing and post-processing.